services:
  llm-api:
    container_name: llm-api
    image: ghcr.io/asepharyana/asepharyana-hub/llm-api:sha-e953c3c
    restart: always
    networks:
      app-shared-net:
        aliases:
          - llm-api
    env_file:
      - ../../.env
    environment:
      - MODEL_PATH=/models/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-Q8_0.gguf
      - API_KEY=${LLM_API_KEY:-}
    volumes:
      - /root/models/gguf:/models:ro
    healthcheck:
      test: ['CMD-SHELL', 'curl -so /dev/null --connect-timeout 5 http://localhost:8080/health || test $? -eq 22']
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    labels:
      prometheus.io/scrape: "true"
      prometheus.io/port: "8080"
    deploy:
      resources:
        limits:
          memory: 2G
        reservations:
          memory: 1G

networks:
  app-shared-net:
    name: app-shared-net
    external: true